{"list":"other","total":73,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189},{"id":"1811.09720","title":"Representer Point Selection for Explaining Deep Neural Networks","created":"2018-11-23","cited_by_count":187},{"id":"2110.14049","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","created":"2021-10-26","cited_by_count":165},{"id":"2310.05175","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","created":"2023-10-08","cited_by_count":165},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150},{"id":"1908.08619","title":"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms","created":"2019-08-22","cited_by_count":148},{"id":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132},{"id":"2004.11207","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","created":"2020-04-23","cited_by_count":125},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123},{"id":"2012.15781","title":"FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging","created":"2020-12-31","cited_by_count":120},{"id":"2310.18339","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","created":"2023-10-21","cited_by_count":111},{"id":"2402.08562","title":"Higher Layers Need More LoRA Experts","created":"2024-02-13","cited_by_count":102},{"id":"2403.02181","title":"Not All Layers of LLMs Are Necessary During Inference","created":"2024-03-04","cited_by_count":96},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94},{"id":"2312.09979","title":"LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin","created":"2023-12-15","cited_by_count":82},{"id":"2102.05262","title":"Input Similarity from the Neural Network Perspective","created":"2021-02-10","cited_by_count":79},{"id":"2402.11260","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","created":"2024-02-17","cited_by_count":63},{"id":"2402.12851","title":"MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models","created":"2024-02-20","cited_by_count":56},{"id":"1901.10501","title":"Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions","created":"2019-01-29","cited_by_count":48},{"id":"2403.03432","title":"Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models","created":"2024-03-06","cited_by_count":38},{"id":"2311.00913","title":"Self-Influence Guided Data Reweighting for Language Model Pre-training","created":"2023-11-02","cited_by_count":37},{"id":"2409.14381","title":"Investigating Layer Importance in Large Language Models","created":"2024-09-22","cited_by_count":36},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34},{"id":"2305.16971","title":"Theoretical and Practical Perspectives on what Influence Functions Do","created":"2023-05-26","cited_by_count":29},{"id":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20},{"id":"2410.10054","title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality","created":"2024-10-14","cited_by_count":20},{"id":"2302.13959","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","created":"2023-02-27","cited_by_count":19},{"id":"2410.12178","title":"Model Balancing Helps Low-data Training and Fine-tuning","created":"2024-10-16","cited_by_count":11},{"id":"2405.03869","title":"Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models","created":"2024-05-06","cited_by_count":10},{"id":"2501.01473","title":"Unraveling Indirect In-Context Learning Using Influence Functions","created":"2025-01-01","cited_by_count":3}],"next_cursor":null}